Skip to main content
An Agent is a connected software actor. The way an Agent appears depends on which workspace you are using.

​
Agents in a buyer organization

In a buyer workspace, Agents are first-class organization resources alongside Advertisers. A buyer agent is software installed into the organization; it is not a person, the account is not classified as agent-driven, and a human user is not tied to an agent. Six related concepts remain intentionally separate:
  • The Agent is the named software actor and its purpose.
  • Its installation is the Agent’s presence in one buyer organization.
  • Its principal is the durable internal identity used for routing and audit.
  • A credential lets the software prove that identity without sharing a human login.
  • A connection lets the Agent exchange supported data or use an organization-owned resource, such as a reporting database, bucket, or file drop. The resource and its credential belong to the organization, not the Agent.
  • A grant is explicit permission for an advertiser or account. Connections, credentials, and principals never imply a grant.
Organization administrators add and manage these Agents from Agents in the buyer navigation. Until a supported grant workflow gives an Agent access, its Access page says No advertiser access. Spend, payment, and Terms authority remain separate and are never inferred. One buyer organization can eventually manage external connected installations and Interchange-hosted installations in this same area. Operation mode changes the operational readback, not the organization or account type. The current supported Add agent flows connect external software; hosted creation waits for the production installation and provisioning contract. Machine-event subscriptions into an Agent belong under Notifications. Organization-owned output destinations that an Agent may be allowed to use, such as an approved Slack connection, remain separate connection resources. Future Slack, email, or inbox notifications for people are a third, human-facing concept and are not represented as machine subscriptions. See Manage buyer agents for the console, credential, connection, and security workflows.

​
Agents that power seller inventory

In a seller workspace, an Agent is an organization-owned software capability. It has its own identity, role, production implementation, certification, and implementation health. An Agent is not necessarily a Sales Agent. For Sales Agents, a Source is the storefront-specific connection to that Agent. The Source owns its credentials, reachability, mappings, and transaction health. The Agent owns the shared implementation and certification facts. Request eligibility and health are separate at both levels. A Source can have a permissions or credential problem while its shared Agent is healthy, and an Agent problem can affect several Sources. Interchange continues sending requests to degraded or erroring Sources while they remain explicitly eligible; only an explicit Source- or Agent-level ineligibility decision stops routing. The Agents preview is currently available only to enrolled organizations.

​
Create an Agent

A directly authenticated organization administrator can choose Create Agent from the Agents collection. The Task creates a private organization-owned Agent and requires its role. A Sales Agent also requires an explicit product mode: Wholesale, Composing, or Both. The Task either selects a claimed operator the organization already owns or creates a separately named operator at the same time. The operator is the secondary company/provider identity; the Agent remains its own capability. Creation establishes only the reusable Agent identity. It does not make the Agent public or a Partner listing, and it does not request credentials, select an authentication method or Source lane, create a Source, or establish a production implementation. Those are separate connection, Source, and versioned-certification workflows. This endpoint requires that same directly authenticated account-admin session; service tokens, delegated sessions, impersonation, and staff-assisted contexts cannot create Agents. Reuse an idempotency UUID only to retry the same request.

​
Review your organization’s Agents

Organization administrators can open Agents from the account navigation to see the Agents their organization operates. The collection identifies each Agent, its role and operator, certification state, implementation health, and the one next action selected by the service. Agents remains the primary destination in the Agent workspace. Organizations with client-management access also see Clients nested beneath it; other organizations keep the same Agents navigation without a Clients destination. Use these endpoints while authenticated as an organization administrator:
An agent working in one of the organization’s Buyer or Seller accounts can use the account-resolved V3 MCP reads instead:
This V3 noun means software Agents the active organization owns. It is not an alias for a Storefront or another buyer counterparty. The compact response includes customer-safe certification and implementation-health facts, but omits operator identifiers, claim state, private certification evidence, relationship identities, credentials, and owner-only action URLs. The certification include expands the public policy, requirement, expiry, and recurring-canary summary. validationRuns adds at most five recent, server-verified run summaries with outcome, cleanup status, accountable failure layer, safe error code, and an exact-read directive. The diagnostics include adds the observed implementation health and current production-revision label. A Sales Agent detail also returns the immutable versioned validationSkill entry to run through ordinary V3 calls. To inspect one returned run without putting every retained request and response in model context, repeat the Agent read with its exact server-issued run ID:
The exact graph contains ordered Activity and request identifiers, the workflow step and V3 operation, platform dispatch outcomes, outbound Agent-call method and status, and the last completed and failed stages. It never returns endpoint URLs, request or response payloads, credentials, private prompts, raw creatives, or customer object identifiers. Caller-supplied workflow annotations group the graph but cannot bind it to an Agent: Interchange returns a run here only after durable server evidence binds that run to the exact Agent revision. Exact private evidence remains on the governed certification surface. Inside Murph, Agents is a full workspace alongside Inventory and Advertisers. Choose an Agent from the rail, then use that same rail to move between its sections. On a narrow screen, Agent and section selectors appear above the Page. Direct links and external MCP hosts show the equivalent section tabs inside the portable Page. The Agent Page has four bounded sections:
  • Overview identifies the Agent, its operator, role, shared implementation, trust states, and the one next action selected by the service.
  • Endpoint & protocol holds the shared, non-secret connection contract and production revision. Credentials, credential expiry, reachability, mappings, and request failures stay with each exact Inventory Source.
  • Test & certify shows the public certification decision, policy version, revision, expiry, and requirement results for a Sales Agent. Governed review actions and private evidence remain in the certification queue. For other Agent roles, this section is labeled Test and does not invent Sales certification requirements.
  • Inventory sources lists the Sales Agent deployments the viewer is authorized to identify and links each one to its Inventory Source details. An Inventory Source owns credentials, authentication, reachability, mappings, failures, and transaction evidence. When Partner operations are active, Invite a client Storefront opens client onboarding with this exact Agent selected and shows this Agent’s pending invitations. An invitation starts a relationship request; it does not yet create an Inventory Source or grant account access. The equivalent future relationship section for a non-Sales Agent stays hidden until that role has a supported connection contract.
Use ?section=overview, ?section=endpoint, ?section=test, or ?section=connections to deep-link to a section. The stable path remains /{organizationId}/agents/{agentId}. The API uses CONNECTIONS as the stable section identifier even when the Sales label is Inventory sources. Navigation links returned to an MCP app are absolute URLs on the applicable Interchange or admin origin, so the same action works from any supported host. The detail response never returns Source credentials, private certification evidence, or another organization’s Source identities. An Agent owner can see an aggregate relationship count while client-specific relationships outside their authority remain hidden.

​
Test a Sales Agent

A claimed owner can open Test & certify and choose a validation profile. The Page currently enables only brief-only; the remaining profiles stay visible as an explicit roadmap and cannot be launched:
  • brief-only temporarily enables the exact Seller for a synthetic sandbox Advertiser, discovers products, then restores DEFAULT and cleans up the temporary Campaign and Advertiser.
  • transaction remains unavailable until the Page runner supports the required multi-confirmation continuation for a no-spend own-supply MediaBuy.
  • complete-floor remains unavailable while the transaction profile cannot run from the Page.
  • rerun-failed remains visibly unavailable until an ordinary V3 read can reconstruct the exact failed run and its inputs.
  • creative remains visibly unavailable until the public skill has an approved executable creative fixture.
Choose Run validation skill. The Page runner remains pinned to the immutable, currently-published test-sales-agent bundle, resolves the current Agent revision, and uses only ordinary /mcp/v3 tools against an owned-inventory Advertiser with sandbox: true and the authenticated Media Company’s own Seller. If Murph requests a confirmation, reply in the inline field; Interchange keeps the same conversation and re-resolves authority on every ordinary call. The Page never receives a fixture token or Source credential. The owner-run Page uses the Media Company’s isolated, no-spend own-supply sandbox. It does not require a separate Buyer Account and does not ask you to choose one. Saving a Source as No auth completes the credential step; it does not need a placeholder secret before validation can run. To test one deployment instead, open that Source’s diagnostics and choose Run validation skill there. The launch is bound to the exact Agent and Source IDs, and products that cannot prove that Source attribution are rejected. Powered-by and admin Agent views may open the public instructions but cannot run the owner’s validation control. An external MCP host follows the same path from scratch:
  1. Call get with kind: "agent" and the exact Agent ID.
  2. Fetch the returned validationSkill.skillUrl and manifest version. Do not replace it with a legacy test endpoint.
  3. Execute the selected scenario through the ordinary V3 tools and keep the skill, scenario, workflow, run, and step metadata specified by the skill.
  4. Preserve ordinary confirmations and reverse-order cleanup.
  5. Read the Agent again with include: ["certification", "diagnostics"] and, when a Source is present, read that exact inventory source with include: ["diagnostics"]. Correlate those server reads with the exact run and Activity identifiers returned by the ordinary calls to obtain the customer-safe graph and accountable Agent, Source, caller, or platform stage.
The final report distinguishes observed, failed, unavailable, and unexercised assertions and cleanup status. A validation run never claims certification; Interchange evaluates trusted evidence separately.

​
See which Agent powers a Source

Storefront users can see the trust summary for the Agent powering one of their own inventory Sources:
sourceId is the identifier from your storefront’s inventory-source response. The result is one of these states:
  • ACTIVE — returns the connected Agent’s safe identity, certification, and implementation-health summary.
  • UNMAPPED — the Source has no active Agent connection.
  • REVOKED — the previous Agent connection is no longer authorized.
This endpoint is scoped to the authenticated storefront and Source. It does not reveal the Agent’s other Sources, credentials, evidence, or operator-only controls. The Powered by projection exposes public certification detail for the connected Agent and exactly the caller’s Source. Open that Source for connection and mapping diagnostics; certification and Source health intentionally remain separate trust signals. An ACTIVE result carries the connected Agent’s authority, and the Source Diagnostics Powered by card reads its heading from it:
  • OWNER — the Agent belongs to your own organization. The card reads Your Agent rather than naming an operator, and links to your full Agent Page.
  • POWERED_BY (or ADMIN) — the Agent belongs to another organization. The card reads Powered by Agent name, names the operator, and links to the client-safe Powered by projection of that Agent’s Page.
UNMAPPED reads This source isn’t linked to an agent yet. and REVOKED reads Agent link revoked — Interchange never falls back to URL matching to guess a binding.

​
Connect your own Agent to a Source

A directly authenticated organization administrator can connect an Agent their organization owns to an Inventory Source their organization owns without platform assistance:
This is first-party only, and direct only: the platform resolves the Agent’s actual owning organization itself and rejects the request before writing anything if the Agent does not belong directly to your organization — including an Agent owned by a parent or sibling organization. Hierarchy-wide first-party binding is deferred to future org entity-model work. Cross-organization (Partner) connections are set up by Scope3 for now. If the Agent’s operator was mapped by Scope3 but never explicitly claimed, binding your own Source to it also claims the operator for your organization in the same request — you do not need a separate claim step first. Only AGENT-execution Inventory Sources are eligible; ESA and other platform-managed Sources are not. See Bind your Agent to a Source for the full request and error contract.

​
Availability and access

All Agent reads require authentication. V2 organization-management reads require a directly authenticated organization administrator. V3 compact reads also accept an account-bound machine credential working in that exact Buyer or Seller account; a user-bound credential still requires organization-admin authority. Delegated, simulated, impersonated, and staff-scoped contexts cannot use the owner projection. Source reads require access to the relevant storefront. The V2 Page endpoints are available when your organization is enrolled in the Agents preview or has a granted Partner workspace; otherwise, they are unavailable. The internal governed-administration view is not part of the customer API.